Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater Environment

TL;DR

This paper evaluates the performance of the advanced Segment Anything Model 2 (SAM2) in underwater environments, highlighting its strengths with ground truth prompts and limitations with automatic prompts in marine image segmentation tasks.

Contribution

It provides the first comprehensive assessment of SAM2's effectiveness in underwater segmentation, emphasizing prompt dependency and potential for marine science applications.

Findings

SAM2 performs well with ground truth bounding box prompts

Automatic mode with point prompts shows degraded performance underwater

Evaluation codes and results are publicly available

Abstract

With breakthroughs in large-scale modeling, the Segment Anything Model (SAM) and its extensions have been attempted for applications in various underwater visualization tasks in marine sciences, and have had a significant impact on the academic community. Recently, Meta has further developed the Segment Anything Model 2 (SAM2), which significantly improves running speed and segmentation accuracy compared to its predecessor. This report aims to explore the potential of SAM2 in marine science by evaluating it on the underwater instance segmentation benchmark datasets UIIS and USIS10K. The experiments show that the performance of SAM2 is extremely dependent on the type of user-provided prompts. When using the ground truth bounding box as prompt, SAM2 performed excellently in the underwater instance segmentation domain. However, when running in automatic mode, SAM2's ability with point prompts to sense and segment underwater instances is significantly degraded. It is hoped that this paper will inspire researchers to further explore the SAM model family in the underwater domain. The results and evaluation codes in this paper are available at https://github.com/LiamLian0727/UnderwaterSAM2Eval.